Optimal Policies for Quantum Markov Decision Processes

被引：0

作者：

Ming-Sheng Ying

Yuan Feng

Sheng-Gang Ying

机构：

[1] University of Technology,Centre for Quantum Software and Information

[2] Chinese Academy of Sciences,State Key Laboratory of Computer Science, Institute of Software

[3] Tsinghua University,Department of Computer Science and Technology

来源：

International Journal of Automation and Computing | 2021年 / 18卷

关键词：

Quantum Markov decision processes; quantum machine learning; reinforcement learning; dynamic programming; decision making;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Markov decision process (MDP) offers a general framework for modelling sequential decision making where outcomes are random. In particular, it serves as a mathematical framework for reinforcement learning. This paper introduces an extension of MDP, namely quantum MDP (qMDP), that can serve as a mathematical model of decision making about quantum systems. We develop dynamic programming algorithms for policy evaluation and finding optimal policies for qMDPs in the case of finite-horizon. The results obtained in this paper provide some useful mathematical tools for reinforcement learning techniques applied to the quantum world.

引用

页码：410 / 421

页数：11

共 50 条

[31] On the convergence of optimal actions for Markov decision processes and the optimality of (s, S) inventory policies
Feinberg, Eugene A.
Lewis, Mark E.
NAVAL RESEARCH LOGISTICS, 2018, 65 (08) : 619 - 637
[32] A note on the existence of optimal stationary policies for average Markov decision processes with countable states
Xia, Li
Guo, Xianping
Cao, Xi-Ren
AUTOMATICA, 2023, 151
[33] Building Optimal Operation Policies for Dam Management Using Factored Markov Decision Processes
Reyes, Alberto
Ibargueengoytia, Pablo H.
Romero, Ines
Pech, David
Borunda, Monica
ADVANCES IN ARTIFICIAL INTELLIGENCE AND ITS APPLICATIONS, MICAI 2015, PT II, 2015, 9414 : 475 - 484
[34] Convex Synthesis of Optimal Policies for Markov Decision Processes with Sequentially-Observed Transitions
El Chamie, Mahmoud
Acikmese, Behcet
2016 AMERICAN CONTROL CONFERENCE (ACC), 2016, : 3862 - 3867
[35] Approximation of average cost optimal policies for general Markov decision processes with unbounded costs
Evgueni Gordienko
Raúl Montes-De-Oca
Adolfo Minjárez-Sosa
Mathematical Methods of Operations Research, 1997, 45 : 245 - 263
[36] STRONG 1-OPTIMAL STATIONARY POLICIES IN DENUMERABLE MARKOV DECISION-PROCESSES
CAVAZOSCADENA, R
LASSERRE, JB
SYSTEMS & CONTROL LETTERS, 1988, 11 (01) : 65 - 71
[37] EXISTENCE OF OPTIMAL STATIONARY POLICIES IN DISCOUNTED MARKOV DECISION-PROCESSES - APPROACHES BY OCCUPATION MEASURES
KURANO, M
KAWAI, M
COMPUTERS & MATHEMATICS WITH APPLICATIONS, 1994, 27 (9-10) : 95 - 101
[38] The effect of eligibility traces on finding optimal memoryless policies in partially observable Markov decision processes
Loch, J
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 11, 1999, 11 : 1010 - 1016
[39] UTILITY OPTIMAL POLICIES IN AN UNDISCOUNTED MARKOV DECISION PROCESS
JAQUETTE, SC
OPERATIONS RESEARCH, 1975, 23 : B353 - B353
[40] A NEW CONDITION FOR THE EXISTENCE OF OPTIMAL STATIONARY POLICIES IN AVERAGE COST MARKOV DECISION-PROCESSES
SENNOTT, LI
OPERATIONS RESEARCH LETTERS, 1986, 5 (01) : 17 - 23

← 1 2 3 4 5 →